Deepak Vijaywargi

  • Citations Per Year
Learn More
We present an overview of the data collection and transcription efforts for the COnversational Speech In Noisy Environments (COSINE) corpus. The corpus is a set of multi-party conversations recorded in real world environments, with background noise, that can be used to train noise-robust speech recognition systems or develop speech de-noising algorithms. We(More)
A certificate of authenticity (COA) is an inexpensive physical object with a random and unique structure S which is hard to nearexactly replicate. An inexpensive device should be able to scan object’s physical “fingerprint,” a set of features that represents S. In this paper, we explore the requirements that optical media such as DVDs should satisfy, to be(More)
We propose a simple, user-friendly tool which aims to offer comparative shopping to the consumer with minimal distraction. The key idea is to detect whether a specific Web-page is commercial, i.e., whether it sells an individual product or service. The detection is performed in real-time at the client with focus on exceptionally low false positives. For(More)
We propose a novel speech enhancement technique based on the hypothesized Wiener filter (HWF) methodology. The proposed HWF algorithm selects a filter for enhancing the input noisy signal by first ‘hypothesizing’ a set of filters and then choosing the most appropriate one for the actual filtering. We show that the proposed HWF can intrinsically offer(More)
  • 1